def test_peaks_plot(self):
data = self.data.copy()
data[30] = 100
data[60] = 40
threshold = 10
peaks = findpeaks.find_peaks2_short(data, threshold, 3)
fig = peaks_plot(data=data, starttime=UTCDateTime("2008001"),
samp_rate=10, peaks=peaks, show=False,
return_figure=True)
return fig
def _median_window(window,
window_start,
multiplier,
starttime,
sampling_rate,
debug=0):
"""
Internal function to aid parallel processing
:type window: numpy.ndarry
:param window: Data to look for peaks in.
:type window_start: int
:param window_start: Index of window start point in larger array, used \
for peak indexing.
:type multiplier: float
:param multiplier: Multiple of MAD to use as threshold
:type starttime: obspy.core.utcdatetime.UTCDateTime
:param starttime: Starttime of window, used in debug plotting.
:type sampling_rate: float
:param sampling_rate in Hz, used for debug plotting
:type debug: int
:param debug: debug level, if want plots, >= 4.
:returns: peaks
:rtype: list
"""
from eqcorrscan.utils.findpeaks import find_peaks2_short
from eqcorrscan.utils.plotting import peaks_plot
MAD = np.median(np.abs(window))
thresh = multiplier * MAD
if debug >= 2:
print('Threshold for window is: ' + str(thresh) + '\nMedian is: ' +
str(MAD) + '\nMax is: ' + str(np.max(window)))
peaks = find_peaks2_short(arr=window, thresh=thresh, trig_int=5, debug=0)
if debug >= 4 and peaks:
peaks_plot(window, starttime, sampling_rate, save=False, peaks=peaks)
if peaks:
peaks = [(peak[0], peak[1] + window_start) for peak in peaks]
else:
peaks = []
return peaks
def _median_window(window, window_start, multiplier, starttime, sampling_rate,
debug=0):
"""Internal function to aid parallel processing
:type window: np.ndarry
:param window: Data to look for peaks in.
:type window_start: int
:param window_start: Index of window start point in larger array, used \
for peak indexing.
:type multiplier: float
:param multiplier: Multiple of MAD to use as threshold
:type starttime: obspy.UTCDateTime
:param starttime: Starttime of window, used in debug plotting.
:type sampling_rate: float
:param sampling_rate in Hz, used for debug plotting
:type debug: int
:param debug: debug level, if want plots, >= 4.
:returns: peaks
"""
from eqcorrscan.utils.findpeaks import find_peaks2_short
from eqcorrscan.utils.plotting import peaks_plot
MAD = np.median(np.abs(window))
thresh = multiplier * MAD
if debug >= 2:
print('Threshold for window is: ' + str(thresh) +
'\nMedian is: ' + str(MAD) +
'\nMax is: ' + str(np.max(window)))
peaks = find_peaks2_short(arr=window,
thresh=thresh, trig_int=5, debug=0)
if debug >= 4 and peaks:
peaks_plot(window, starttime, sampling_rate,
save=False, peaks=peaks)
if peaks:
peaks = [(peak[0], peak[1] + window_start) for peak in peaks]
else:
peaks = []
return peaks
def find_peaks2_short(arr, thresh, trig_int, debug=0, starttime=False,
samp_rate=1.0):
"""
Determine peaks in an array of data above a certain threshold.
Uses a mask to remove data below threshold and finds peaks in what is left.
:type arr: numpy.ndarray
:param arr: 1-D numpy array is required
:type thresh: float
:param thresh: The threshold below which will be considered noise and \
peaks will not be found in.
:type trig_int: int
:param trig_int: The minimum difference in samples between triggers,\
if multiple peaks within this window this code will find the highest.
:type debug: int
:param debug: Optional, debug level 0-5
:type starttime: obspy.core.utcdatetime.UTCDateTime
:param starttime: Starttime for plotting, only used if debug > 2.
:type samp_rate: float
:param samp_rate: Sampling rate in Hz, only used for plotting if debug > 2.
:return: peaks: Lists of tuples of peak values and locations.
:rtype: list
>>> import numpy as np
>>> arr = np.random.randn(100)
>>> threshold = 10
>>> arr[40] = 20
>>> arr[60] = 100
>>> find_peaks2_short(arr, threshold, 3)
[(20.0, 40), (100.0, 60)]
"""
if not starttime:
starttime = UTCDateTime(0)
# Set everything below the threshold to zero
image = np.copy(arr)
image = np.abs(image)
image[image < thresh] = 0
if len(image[image > thresh]) == 0:
if debug > 0:
print('No values over threshold found')
return []
if debug > 0:
print(' '.join(['Found', str(len(image[image > thresh])),
'samples above the threshold']))
initial_peaks = []
peaks = []
# Find the peaks
labeled_image, number_of_objects = ndimage.label(image)
peak_slices = ndimage.find_objects(labeled_image)
for peak_slice in peak_slices:
# print('Width of peak='+str(peak_slice[0].stop-peak_slice[0].start)
window = arr[peak_slice[0].start: peak_slice[0].stop]
initial_peaks.append((max(window),
int(peak_slice[0].start + np.argmax(window))))
if initial_peaks:
peaks = decluster(peaks=initial_peaks, trig_int=trig_int, debug=debug)
if debug >= 3:
from eqcorrscan.utils import plotting
_fname = ''.join(['peaks_',
starttime.datetime.strftime('%Y-%m-%d'),
'.pdf'])
plotting.peaks_plot(data=image, starttime=starttime,
samp_rate=samp_rate, save=True,
peaks=peaks, savefile=_fname)
peaks = sorted(peaks, key=lambda time: time[1], reverse=False)
return peaks
else:
print('No peaks for you!')
return peaks
def find_peaks2_short(arr,
thresh,
trig_int,
debug=0,
starttime=False,
samp_rate=1.0,
full_peaks=False):
"""
Determine peaks in an array of data above a certain threshold.
Uses a mask to remove data below threshold and finds peaks in what is left.
:type arr: numpy.ndarray
:param arr: 1-D numpy array is required
:type thresh: float
:param thresh:
The threshold below which will be considered noise and peaks will
not be found in.
:type trig_int: int
:param trig_int:
The minimum difference in samples between triggers, if multiple
peaks within this window this code will find the highest.
:type debug: int
:param debug: Optional, debug level 0-5
:type starttime: obspy.core.utcdatetime.UTCDateTime
:param starttime: Starttime for plotting, only used if debug > 2.
:type samp_rate: float
:param samp_rate: Sampling rate in Hz, only used for plotting if debug > 2.
:type full_peaks: bool
:param full_peaks:
If True, will remove the issue eluded to below, by declustering within
data-sections above the threshold, rather than just taking the peak
within that section. This will take more time. This defaults to True
for match_filter.
:return: peaks: Lists of tuples of peak values and locations.
:rtype: list
>>> import numpy as np
>>> arr = np.random.randn(100)
>>> threshold = 10
>>> arr[40] = 20
>>> arr[60] = 100
>>> find_peaks2_short(arr, threshold, 3)
[(20.0, 40), (100.0, 60)]
.. note::
peak-finding is optimised for zero-mean cross-correlation data where
fluctuations are frequent. Because of this, in certain cases some
peaks may be missed if the trig_int is short and the threshold is low.
Consider the following case:
>>> arr = np.array([1, .2, .2, .2, .2, 1, .2, .2, .2, .2, 1])
>>> find_peaks2_short(arr, thresh=.2, trig_int=3)
[(1.0, 0)]
Whereas you would expect the following:
>>> arr = np.array([1, .2, .2, .2, .2, 1, .2, .2, .2, .2, 1])
>>> find_peaks2_short(arr, thresh=.2, trig_int=3, full_peaks=True)
[(1.0, 0), (1.0, 5), (1.0, 10)]
This is rare and unlikely to happen for correlation cases, where
trigger intervals are usually large and thresholds high.
"""
if not starttime:
starttime = UTCDateTime(0)
# Set everything below the threshold to zero
image = np.copy(arr)
image = np.abs(image)
debug_print("Threshold: {0}\tMax: {1}".format(thresh, max(image)), 2,
debug)
image[image < thresh] = 0
if len(image[image > thresh]) == 0:
debug_print("No values over threshold {0}".format(thresh), 0, debug)
return []
debug_print(
'Found {0} samples above the threshold'.format(
len(image[image > thresh])), 0, debug)
initial_peaks = []
# Find the peaks
labeled_image, number_of_objects = ndimage.label(image)
peak_slices = ndimage.find_objects(labeled_image)
for peak_slice in peak_slices:
window = arr[peak_slice[0].start:peak_slice[0].stop]
if peak_slice[0].stop - peak_slice[0].start > trig_int and full_peaks:
peaks = decluster(peaks=window,
trig_int=trig_int,
index=np.arange(peak_slice[0].start,
peak_slice[0].stop))
else:
peaks = [(window[np.argmax(abs(window))],
int(peak_slice[0].start + np.argmax(abs(window))))]
initial_peaks.extend(peaks)
peaks = decluster(peaks=np.array(list(zip(*initial_peaks))[0]),
index=np.array(list(zip(*initial_peaks))[1]),
trig_int=trig_int)
if initial_peaks:
if debug >= 3:
from eqcorrscan.utils import plotting
_fname = ''.join(
['peaks_',
starttime.datetime.strftime('%Y-%m-%d'), '.pdf'])
plotting.peaks_plot(data=image,
starttime=starttime,
samp_rate=samp_rate,
save=True,
peaks=peaks,
savefile=_fname)
peaks = sorted(peaks, key=lambda time: time[1], reverse=False)
return peaks
else:
print('No peaks for you!')
return []
def find_peaks2(arr, thresh, trig_int, debug=0, maxwidth=10,
starttime=False, samp_rate=1.0):
r"""Function to determine peaks in an array of data using scipy \
find_peaks_cwt, works fast in certain cases, but for match_filter cccsum \
peak finding, find_peaks2_short works better. Test it out and see which \
works best for your application.
:type arr: ndarray
:param arr: 1-D numpy array is required
:type thresh: float
:param thresh: The threshold below which will be considered noise and \
peaks will not be found in.
:type trig_int: int
:param trig_int: The minimum difference in samples between triggers, \
if multiple peaks within this window this code will find the highest.
:type debug: int
:param debug: Optional, debug level 0-5
:type maxwidth: int
:param maxwidth: Maximum peak width to look for in samples
:type starttime: osbpy.UTCDateTime
:param starttime: Starttime for plotting, only used if debug > 2.
:type samp_rate: float
:param samp_rate: Sampling rate in Hz, only used for plotting if debug > 2.
:return: peaks: Lists of tuples of peak values and locations.
"""
from scipy.signal import find_peaks_cwt
import numpy as np
from obspy import UTCDateTime
if not starttime:
starttime = UTCDateTime(0)
# Set everything below the threshold to zero
image = np.copy(arr)
image = np.abs(image)
image[image < thresh] = thresh
# We need to check if the number of samples in the image is prime, if it
# is this method will be really slow, so we add a pad to the end to make
# it not of prime length!
if is_prime(len(image)):
image = np.append(image, 0.0)
print('Input array has a prime number of samples, appending a zero')
print(len(image))
if len(image[image > thresh]) == 0:
print('No values over threshold found')
return []
if debug > 0:
msg = ' '.join(['Found', str(len(image[image > thresh])),
'samples above the threshold'])
print(msg)
initial_peaks = []
peaks = []
# Find the peaks
print('Finding peaks')
peakinds = find_peaks_cwt(image, np.arange(1, maxwidth))
initial_peaks = [(image[peakind], peakind) for peakind in peakinds]
# Sort initial peaks according to amplitude
print('sorting peaks')
peaks_sort = sorted(initial_peaks, key=lambda amplitude: amplitude[0],
reverse=True)
if debug >= 4:
for peak in initial_peaks:
print(peak)
if initial_peaks:
peaks.append(peaks_sort[0]) # Definitely take the biggest peak
if debug > 3:
msg = ' '.join(['Added the biggest peak of', str(peaks[0][0]),
'at sample', str(peaks[0][1])])
print(msg)
if len(initial_peaks) > 1:
if debug > 3:
msg = ' '.join(['Multiple peaks found, checking them',
'now to see if they overlap'])
print(msg)
for next_peak in peaks_sort:
# i in xrange(1,len(peaks_sort)):
# Loop through the amplitude sorted peaks
# if the next highest amplitude peak is within trig_int of any
# peak already in peaks then we don't want it, else, add it
# next_peak = peaks_sort[i]
if debug > 3:
print(next_peak)
for peak in peaks:
add = False
# Use add as a switch for whether or not to append
# next peak to peaks, if once gone through all the peaks
# it is True, then we will add it, otherwise we won't!
if abs(next_peak[1] - peak[1]) < trig_int:
if debug > 3:
msg = ' '.join(['Difference in time is',
str(next_peak[1] - peak[1]), '\n'
'Which is less than',
str(trig_int)])
print(msg)
add = False
# Need to exit the loop here if false
break
else:
add = True
if add:
if debug > 3:
msg = ' '.join(['Adding peak of', str(next_peak[0]),
'at sample', str(next_peak[1])])
print(msg)
peaks.append(next_peak)
elif debug > 3:
msg = ' '.join(['I did not add peak of',
str(next_peak[0]), 'at sample',
str(next_peak[1])])
print(msg)
if debug >= 3:
from eqcorrscan.utils import plotting
_fname = ''.join(['peaks_',
starttime.datetime.strftime('%Y-%m-%d'),
'.pdf'])
print(' '.join(['Saving plot to', _fname]))
plotting.peaks_plot(image, starttime, samp_rate, True,
peaks, _fname)
peaks = sorted(peaks, key=lambda time: time[1], reverse=False)
return peaks
else:
print('No peaks for you!')
return peaks
def find_peaks_dep(arr, thresh, trig_int, debug=0, starttime=False,
samp_rate=1.0):
r"""Function to determine peaks in an array of data above a certain \
threshold.
Depreciated peak-finding routine, very slow, but accurate. If all else \
fails this one should work.
:type arr: ndarray
:param arr: 1-D numpy array is required
:type thresh: float
:param thresh: The threshold below which will be considered noise and \
peaks will not be found in.
:type trig_int: int
:param trig_int: The minimum difference in samples between triggers,\
if multiple peaks within this window this code will find the highest.
:type starttime: osbpy.UTCDateTime
:param starttime: Starttime for plotting, only used if debug > 2.
:type samp_rate: float
:param samp_rate: Sampling rate in Hz, only used for plotting if debug > 2.
:return: peaks: Lists of tuples of peak values and locations.
"""
import numpy as np
from obspy import UTCDateTime
if not starttime:
starttime = UTCDateTime(0)
# Perform some checks
if trig_int < 3:
msg = 'Trigger interval must be greater than 2 samples to find maxima'
raise IOError(msg)
# from joblib import Parallel, delayed
# Will find peaks in the absolute then transfer these to the true values
sig = np.abs(arr) - thresh
true_peaks = []
for i in xrange(int(trig_int), int(len(sig) - trig_int), int(trig_int)):
window = sig[i - trig_int: i + trig_int]
# Define a moving window containing data from +/- the trigger iterval
peaks = []
locs = []
for j in xrange(1, len(window) - 1):
# Find all turning points within the window
if window[j] > 0.0 and window[j] > window[j+1] and\
window[j] > window[j - 1]:
peaks.append(window[j])
locs.append(i - trig_int + j)
# Find maximum peak in window
if peaks:
true_peaks.append((np.max(np.array(peaks)),
locs[np.argmax(np.array(peaks))]))
# Get unique values
peaks = sorted(list(set(true_peaks)), key=lambda loc: loc[1])
# Find highest peak in peaks within trig_int of each other
for i in xrange(1, len(peaks) - 1):
if peaks[i + 1][1]-peaks[i][1] < trig_int:
if peaks[i][0] < peaks[i + 1][0]:
peaks[i] = peaks[i + 1]
else:
peaks[i + 1] = peaks[i]
elif peaks[i][1] - peaks[i - 1][1] < trig_int:
if peaks[i][0] < peaks[i - 1][0]:
peaks[i] = peaks[i - 1]
else:
peaks[i - 1] = peaks[i]
peaks = sorted(list(set(peaks)), key=lambda loc: loc[1])
if debug >= 3:
from eqcorrscan.utils import plotting
_fname = ''.join(['peaks_',
starttime.datetime.strftime('%Y-%m-%d'),
'.pdf'])
plotting.peaks_plot(arr, starttime, samp_rate, True, peaks,
_fname)
return peaks
def find_peaks2_short(arr, thresh, trig_int, debug=0, starttime=False,
samp_rate=1.0):
r"""Function to determine peaks in an array of data above a certain \
threshold. Uses a mask to remove data below threshold and finds peaks in \
what is left.
:type arr: ndarray
:param arr: 1-D numpy array is required
:type thresh: float
:param thresh: The threshold below which will be considered noise and \
peaks will not be found in.
:type trig_int: int
:param trig_int: The minimum difference in samples between triggers,\
if multiple peaks within this window this code will find the highest.
:type debug: int
:param debug: Optional, debug level 0-5
:type starttime: osbpy.UTCDateTime
:param starttime: Starttime for plotting, only used if debug > 2.
:type samp_rate: float
:param samp_rate: Sampling rate in Hz, only used for plotting if debug > 2.
:return: peaks: Lists of tuples of peak values and locations.
"""
from scipy import ndimage
import numpy as np
from obspy import UTCDateTime
if not starttime:
starttime = UTCDateTime(0)
# Set everything below the threshold to zero
image = np.copy(arr)
image = np.abs(image)
image[image < thresh] = 0
if len(image[image > thresh]) == 0:
print('No values over threshold found')
return []
if debug > 0:
print(' '.join(['Found', str(len(image[image > thresh])),
'samples above the threshold']))
initial_peaks = []
peaks = []
# Find the peaks
labeled_image, number_of_objects = ndimage.label(image)
peak_slices = ndimage.find_objects(labeled_image)
for peak_slice in peak_slices:
# print('Width of peak='+str(peak_slice[0].stop-peak_slice[0].start)
window = arr[peak_slice[0].start: peak_slice[0].stop]
initial_peaks.append((max(window),
peak_slice[0].start + np.argmax(window)))
# Sort initial peaks according to amplitude
peaks_sort = sorted(initial_peaks, key=lambda amplitude: amplitude[0],
reverse=True)
# Debugging
if debug >= 4:
for peak in initial_peaks:
print(peak)
if initial_peaks:
peaks.append(peaks_sort[0]) # Definitely take the biggest peak
if debug > 3:
print(' '.join(['Added the biggest peak of', str(peaks[0][0]),
'at sample', str(peaks[0][1])]))
if len(initial_peaks) > 1:
if debug > 3:
msg = ' '.join(['Multiple peaks found, checking',
'them now to see if they overlap'])
print(msg)
for next_peak in peaks_sort:
# i in xrange(1,len(peaks_sort)):
# Loop through the amplitude sorted peaks
# if the next highest amplitude peak is within trig_int of any
# peak already in peaks then we don't want it, else, add it
# next_peak=peaks_sort[i]
if debug > 3:
print(next_peak)
for peak in peaks:
add = False
# Use add as a switch for whether or not to append
# next peak to peaks, if once gone through all the peaks
# it is True, then we will add it, otherwise we won't!
if abs(next_peak[1]-peak[1]) < trig_int:
if debug > 3:
msg = ' '.join(['Difference in time is',
str(next_peak[1]-peak[1]), '\n',
'Which is less than',
str(trig_int)])
print(msg)
add = False
# Need to exit the loop here if false
break
else:
add = True
if add:
if debug > 3:
msg = ' '.join(['Adding peak of', str(next_peak[0]),
'at sample', str(next_peak[1])])
print(msg)
peaks.append(next_peak)
elif debug > 3:
msg = ' '.join(['I did not add peak of', str(next_peak[0]),
'at sample', str(next_peak[1])])
print(msg)
if debug >= 3:
from eqcorrscan.utils import plotting
_fname = ''.join(['peaks_',
starttime.datetime.strftime('%Y-%m-%d'),
'.pdf'])
plotting.peaks_plot(image, starttime, samp_rate, True,
peaks, _fname)
peaks = sorted(peaks, key=lambda time: time[1], reverse=False)
return peaks
else:
print('No peaks for you!')
return peaks
def find_peaks2_short(arr, thresh, trig_int, debug=0, starttime=False,
samp_rate=1.0):
"""
Determine peaks in an array of data above a certain threshold.
Uses a mask to remove data below threshold and finds peaks in what is left.
:type arr: numpy.ndarray
:param arr: 1-D numpy array is required
:type thresh: float
:param thresh: The threshold below which will be considered noise and \
peaks will not be found in.
:type trig_int: int
:param trig_int: The minimum difference in samples between triggers,\
if multiple peaks within this window this code will find the highest.
:type debug: int
:param debug: Optional, debug level 0-5
:type starttime: obspy.core.utcdatetime.UTCDateTime
:param starttime: Starttime for plotting, only used if debug > 2.
:type samp_rate: float
:param samp_rate: Sampling rate in Hz, only used for plotting if debug > 2.
:return: peaks: Lists of tuples of peak values and locations.
:rtype: list
>>> import numpy as np
>>> arr = np.random.randn(100)
>>> threshold = 10
>>> arr[40] = 20
>>> arr[60] = 100
>>> find_peaks2_short(arr, threshold, 3)
[(20.0, 40), (100.0, 60)]
"""
if not starttime:
starttime = UTCDateTime(0)
# Set everything below the threshold to zero
image = np.copy(arr)
image = np.abs(image)
image[image < thresh] = 0
if len(image[image > thresh]) == 0:
if debug > 0:
print('No values over threshold found')
return []
if debug > 0:
print(' '.join(['Found', str(len(image[image > thresh])),
'samples above the threshold']))
initial_peaks = []
peaks = []
# Find the peaks
labeled_image, number_of_objects = ndimage.label(image)
peak_slices = ndimage.find_objects(labeled_image)
for peak_slice in peak_slices:
# print('Width of peak='+str(peak_slice[0].stop-peak_slice[0].start)
window = arr[peak_slice[0].start: peak_slice[0].stop]
initial_peaks.append((max(window),
int(peak_slice[0].start + np.argmax(window))))
# Sort initial peaks according to amplitude
peaks_sort = sorted(initial_peaks, key=lambda amplitude: amplitude[0],
reverse=True)
# Debugging
if debug >= 4:
for peak in initial_peaks:
print(peak)
if initial_peaks:
peaks.append(peaks_sort[0]) # Definitely take the biggest peak
if debug > 3:
print(' '.join(['Added the biggest peak of', str(peaks[0][0]),
'at sample', str(peaks[0][1])]))
if len(initial_peaks) > 1:
if debug > 3:
msg = ' '.join(['Multiple peaks found, checking',
'them now to see if they overlap'])
print(msg)
for next_peak in peaks_sort:
# i in range(1,len(peaks_sort)):
# Loop through the amplitude sorted peaks
# if the next highest amplitude peak is within trig_int of any
# peak already in peaks then we don't want it, else, add it
# next_peak=peaks_sort[i]
if debug > 3:
print(next_peak)
for peak in peaks:
# Use add as a switch for whether or not to append
# next peak to peaks, if once gone through all the peaks
# it is True, then we will add it, otherwise we won't!
if abs(next_peak[1] - peak[1]) < trig_int:
if debug > 3:
msg = ' '.join(['Difference in time is',
str(next_peak[1] - peak[1]), '\n',
'Which is less than',
str(trig_int)])
print(msg)
add = False
# Need to exit the loop here if false
break
else:
add = True
if add:
if debug > 3:
msg = ' '.join(['Adding peak of', str(next_peak[0]),
'at sample', str(next_peak[1])])
print(msg)
peaks.append(next_peak)
elif debug > 3:
msg = ' '.join(['I did not add peak of', str(next_peak[0]),
'at sample', str(next_peak[1])])
print(msg)
if debug >= 3:
from eqcorrscan.utils import plotting
_fname = ''.join(['peaks_',
starttime.datetime.strftime('%Y-%m-%d'),
'.pdf'])
plotting.peaks_plot(data=image, starttime=starttime,
samp_rate=samp_rate, save=True,
peaks=peaks, savefile=_fname)
peaks = sorted(peaks, key=lambda time: time[1], reverse=False)
return peaks
else:
print('No peaks for you!')
return peaks
def find_peaks_dep(arr, thresh, trig_int, debug=0, starttime=False,
samp_rate=1.0):
"""
Determine peaks in an array of data above a certain threshold: depreciated.
Depreciated peak-finding routine, very slow, but accurate. If all else \
fails this one should work.
:type arr: numpy.ndarray
:param arr: 1-D numpy array is required
:type thresh: float
:param thresh: The threshold below which will be considered noise and \
peaks will not be found in.
:type trig_int: int
:param trig_int: The minimum difference in samples between triggers,\
if multiple peaks within this window this code will find the highest.
:type starttime: obspy.core.utcdatetime.UTCDateTime
:param starttime: Starttime for plotting, only used if debug > 2.
:type samp_rate: float
:param samp_rate: Sampling rate in Hz, only used for plotting if debug > 2.
:return: peaks: Lists of tuples of peak values and locations.
:rtype: list
>>> import numpy as np
>>> arr = np.random.randn(100)
>>> threshold = 10
>>> arr[40] = 20
>>> arr[60] = 100
>>> find_peaks_dep(arr, threshold, 3)
[(20.0, 40), (100.0, 60)]
"""
if not starttime:
starttime = UTCDateTime(0)
# Perform some checks
if trig_int < 3:
msg = 'Trigger interval must be greater than 2 samples to find maxima'
raise IOError(msg)
# from joblib import Parallel, delayed
# Will find peaks in the absolute then transfer these to the true values
sig = np.abs(arr) - thresh
true_peaks = []
for i in range(int(trig_int), int(len(sig) - trig_int), int(trig_int)):
window = sig[i - trig_int: i + trig_int]
# Define a moving window containing data from +/- the trigger iterval
peaks = []
locs = []
for j in range(1, len(window) - 1):
# Find all turning points within the window
if window[j] > 0.0 and window[j] > window[j + 1] and\
window[j] > window[j - 1]:
peaks.append(window[j])
locs.append(i - trig_int + j)
# Find maximum peak in window
if peaks:
true_peaks.append((np.max(np.array(peaks)),
locs[np.argmax(np.array(peaks))]))
# Get unique values
peaks = sorted(list(set(true_peaks)), key=lambda loc: loc[1])
# Find highest peak in peaks within trig_int of each other
for i in range(1, len(peaks) - 1):
if peaks[i + 1][1] - peaks[i][1] < trig_int:
if peaks[i][0] < peaks[i + 1][0]:
peaks[i] = peaks[i + 1]
else:
peaks[i + 1] = peaks[i]
elif peaks[i][1] - peaks[i - 1][1] < trig_int:
if peaks[i][0] < peaks[i - 1][0]:
peaks[i] = peaks[i - 1]
else:
peaks[i - 1] = peaks[i]
peaks = sorted(list(set(peaks)), key=lambda loc: loc[1])
if debug >= 3:
from eqcorrscan.utils import plotting
_fname = ''.join(['peaks_',
starttime.datetime.strftime('%Y-%m-%d'),
'.pdf'])
plotting.peaks_plot(arr, starttime, samp_rate, True, peaks,
_fname)
peaks = [(peak[0] + thresh, peak[1]) for peak in peaks]
return peaks
def find_peaks2(arr,
thresh,
trig_int,
debug=0,
maxwidth=10,
starttime=False,
samp_rate=1.0):
r"""Function to determine peaks in an array of data using scipy \
find_peaks_cwt, works fast in certain cases, but for match_filter cccsum \
peak finding, find_peaks2_short works better. Test it out and see which \
works best for your application.
:type arr: ndarray
:param arr: 1-D numpy array is required
:type thresh: float
:param thresh: The threshold below which will be considered noise and \
peaks will not be found in.
:type trig_int: int
:param trig_int: The minimum difference in samples between triggers, \
if multiple peaks within this window this code will find the highest.
:type debug: int
:param debug: Optional, debug level 0-5
:type maxwidth: int
:param maxwidth: Maximum peak width to look for in samples
:type starttime: osbpy.UTCDateTime
:param starttime: Starttime for plotting, only used if debug > 2.
:type samp_rate: float
:param samp_rate: Sampling rate in Hz, only used for plotting if debug > 2.
:return: peaks: Lists of tuples of peak values and locations.
"""
from scipy.signal import find_peaks_cwt
import numpy as np
from obspy import UTCDateTime
if not starttime:
starttime = UTCDateTime(0)
# Set everything below the threshold to zero
image = np.copy(arr)
image = np.abs(image)
image[image < thresh] = thresh
# We need to check if the number of samples in the image is prime, if it
# is this method will be really slow, so we add a pad to the end to make
# it not of prime length!
if is_prime(len(image)):
image = np.append(image, 0.0)
print('Input array has a prime number of samples, appending a zero')
print(len(image))
if len(image[image > thresh]) == 0:
print('No values over threshold found')
return []
if debug > 0:
msg = ' '.join([
'Found',
str(len(image[image > thresh])), 'samples above the threshold'
])
print(msg)
initial_peaks = []
peaks = []
# Find the peaks
print('Finding peaks')
peakinds = find_peaks_cwt(image, np.arange(1, maxwidth))
initial_peaks = [(image[peakind], peakind) for peakind in peakinds]
# Sort initial peaks according to amplitude
print('sorting peaks')
peaks_sort = sorted(initial_peaks,
key=lambda amplitude: amplitude[0],
reverse=True)
if debug >= 4:
for peak in initial_peaks:
print(peak)
if initial_peaks:
peaks.append(peaks_sort[0]) # Definitely take the biggest peak
if debug > 3:
msg = ' '.join([
'Added the biggest peak of',
str(peaks[0][0]), 'at sample',
str(peaks[0][1])
])
print(msg)
if len(initial_peaks) > 1:
if debug > 3:
msg = ' '.join([
'Multiple peaks found, checking them',
'now to see if they overlap'
])
print(msg)
for next_peak in peaks_sort:
# i in xrange(1,len(peaks_sort)):
# Loop through the amplitude sorted peaks
# if the next highest amplitude peak is within trig_int of any
# peak already in peaks then we don't want it, else, add it
# next_peak = peaks_sort[i]
if debug > 3:
print(next_peak)
for peak in peaks:
add = False
# Use add as a switch for whether or not to append
# next peak to peaks, if once gone through all the peaks
# it is True, then we will add it, otherwise we won't!
if abs(next_peak[1] - peak[1]) < trig_int:
if debug > 3:
msg = ' '.join([
'Difference in time is',
str(next_peak[1] - peak[1]), '\n'
'Which is less than',
str(trig_int)
])
print(msg)
add = False
# Need to exit the loop here if false
break
else:
add = True
if add:
if debug > 3:
msg = ' '.join([
'Adding peak of',
str(next_peak[0]), 'at sample',
str(next_peak[1])
])
print(msg)
peaks.append(next_peak)
elif debug > 3:
msg = ' '.join([
'I did not add peak of',
str(next_peak[0]), 'at sample',
str(next_peak[1])
])
print(msg)
if debug >= 3:
from eqcorrscan.utils import plotting
_fname = ''.join(
['peaks_',
starttime.datetime.strftime('%Y-%m-%d'), '.pdf'])
print(' '.join(['Saving plot to', _fname]))
plotting.peaks_plot(image, starttime, samp_rate, True, peaks,
_fname)
peaks = sorted(peaks, key=lambda time: time[1], reverse=False)
return peaks
else:
print('No peaks for you!')
return peaks
